Research Article
Local Epochs Inefficiency Caused by Device Heterogeneity in Federated Learning
Algorithm 1
Dimensionality reduction.
| Input: weights model, the number of dataset, feature set, dataset , the amount of dataset | | Output: the set of key features | | 1: Initialize | | 2: For each dataset | | 3: ⟵GetWeights | | 4: ⟵rank | | 5: End for | | 6: For in do | | 7: | | 8: | | 9: Ifthen | | 10: AddNewFeature | | 11: End if | | 12: End for | | 13: Return |
|